相关参考文献
注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article
Energy & Fuels
Faisal Aladwani et al.
Summary: Fluid viscosity is crucial in the petroleum industry. This study developed three supervised machine learning regression models to predict viscosity and found that the newly developed models outperformed existing models, with Gaussian process regression and regression ensembles tree showing the best performance.
PETROLEUM SCIENCE AND TECHNOLOGY
(2023)
Article
Chemistry, Multidisciplinary
Alexey N. Beskopylny et al.
Summary: The creation and training of artificial neural networks enable the identification of patterns and hidden relationships in the production of unique building materials, prediction of mechanical properties, and problem-solving in defect detection and classification.
APPLIED SCIENCES-BASEL
(2023)
Article
Engineering, Chemical
Dicho Stratiev et al.
Summary: The precision of petroleum engineering calculations and process design can be affected by the accuracy of petroleum fluid molecular weight correlations. Some methods used in commercial software process simulators for predicting petroleum fluid molecular weight are not significantly better than the Lee-Kesler and Twu correlations, which are the most commonly used in petroleum engineering. In this study, 430 data points for boiling point, specific gravity, and molecular weight of petroleum fluids and individual hydrocarbons were analyzed to determine the most appropriate correlations for petroleum fluids with molecular weight variation. The artificial neural network (ANN) model showed the highest accuracy of prediction, followed by the newly developed nonlinear regression correlation.
Article
Chemistry, Analytical
Pankyu Kim et al.
Summary: In this study, enhanced electrochemical detection of single water-in-oil emulsion droplets was achieved using the nano-impact method. The water molecules in the droplets were directly oxidized without the need for additional electroactive species when the droplets collided with the ultramicroelectrode. Effective electrolysis of the droplets was achieved by considering charge neutrality and limiting reagent. Approximately 10% of the water molecules in the droplet (55.6 M H2O) were oxidized based on electrochemical peak analysis and DLS measurements.
Article
Engineering, Multidisciplinary
Jie Li et al.
Article
Engineering, Chemical
Robert P. Panckow et al.
Summary: This study aims to develop an experimental method to characterize the fluid dynamic stress acting on particles in a lab-scale stirred tank reactor. The method uses a photo-optical inline particle size measurement technique and a Convolutional Neural Network (CNN) for particle detection and analysis. The obtained changes of floc size and shape allow for a more detailed evaluation of particle stress compared to previous studies.
CHEMICAL ENGINEERING SCIENCE
(2023)
Article
Engineering, Electrical & Electronic
Arnaldo Leal-Junior et al.
Summary: This paper presents the development of a fiber optic sensor based on the surface Plasmon resonance (SPR) principle for estimating water content in oil-water emulsions. The sensor is made using a polymer optical fiber (POF) with a gold thin film for the SPR signal. The sensor's sensitivity to water content and transmitted optical power variation is analyzed, and the possibility of data fusion for accurate water content estimation is explored. The paper also addresses the temperature cross-sensitivity issue and proposes a compensation method to reduce temperature-induced errors in water content estimation.
OPTICAL FIBER TECHNOLOGY
(2023)
Review
Energy & Fuels
Songling Huang et al.
Summary: Magnetic flux leakage testing (MFL) is widely used for safety inspection of oil and gas pipelines. Recently, deep-learning technologies have been applied to the analysis of MFL test data with remarkable results. This review comprehensively summarizes the applications of deep learning for MFL detection and evaluation of oil and gas pipelines, covering pipeline anomaly recognition, defect quantification, and MFL data augmentation. The traditional analysis method is compared with deep learning, and potential research challenges and directions are discussed.
Article
Chemistry, Multidisciplinary
Alexey N. Beskopylny et al.
Summary: In recent years, machine vision algorithms have become widely used in industry for visual automatic non-destructive testing. This approach utilizes convolutional neural networks to detect, classify, and segment defects in building materials and structures. Implementing intelligent systems in the early stages of manufacturing can help identify and eliminate defective materials, prevent the spread of defective products, and determine the cause of specific damages.
APPLIED SCIENCES-BASEL
(2023)
Article
Green & Sustainable Science & Technology
Jiajun Liu et al.
Summary: This paper proposes a catchment well oil detection method based on the global relation-aware attention mechanism, which highlights the main features of oil and improves the detection accuracy by embedding the global relation-aware attention mechanism in the backbone network of Yolov5s. Additionally, single-scale retinex histogram equalization is used to enhance the grayscale and contrast of the oil images and improve the details of the dataset images. The experimental results show that the proposed method achieves high accuracy in detecting engine oil and turbine oil pollution, and effectively reduces missing and false detection.
Article
Chemistry, Analytical
Nurliana Farhana Salehuddin et al.
Summary: An automated model based on an artificial neural network was designed to predict Saybolt color. The results showed that the ANN model outperformed the multiple linear regression model in predicting Saybolt color.
Review
Energy & Fuels
Sonia Mir et al.
Summary: This article provides an overview of the state-of-the-art methods of water and oil separation, with a focus on nanomaterial-based filtration methods. By presenting environmental stimuli and finding smart materials, the efficiency of separation can be improved and compete with conventional methods.
JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING
(2022)
Article
Environmental Sciences
Emna Amri et al.
Summary: This paper presents an approach for automated detection of offshore oil slicks using an extensive database of real and recent oil slick monitoring scenarios. The approach relies on annotations performed by expert photo-interpreters on Sentinel-1 SAR data and incorporates contextual data such as wind estimates. It achieves high detection performance and reduces false alarms compared to mono-modal models.
Article
Mathematics
Abdulilah Mohammad Mayet et al.
Summary: The research utilizes a system based on feature extraction technique and neural network to accurately determine the type and amount of petroleum products. The system extracts signal features and inputs them into a neural network for classification, resulting in high prediction accuracy.
Article
Engineering, Multidisciplinary
Jie Li et al.
Summary: This study prepared PDMS/PVDF oil-water separation membranes with designed microstructures using electrospinning technology. It was found that a high PDMS content in the membrane was more likely to form microspheres, which improved the hydrophobicity of the membrane. When the ratio of PDMS to PVDF was 1:2, the membrane exhibited a water contact angle of up to 150 degrees and a separation efficiency of 98.7% for water-in-oil emulsion. The membrane maintained over 98% separation efficiency after ten separation cycles. Furthermore, the membrane had good elongation, fracture strength, and excellent UV resistance, making it a potential UV protective material.
Article
Engineering, Multidisciplinary
Feiran Li et al.
Summary: Effective integrated methods for oil-water separation and water remediation are of great significance in the energy and environment fields. Materials with both superlyophobic and superlyophilic properties are highly desirable due to their energy-saving and high-efficiency advantages. However, the introduction of low surface tension fluorinated components may lead to environmental harm and additional contamination. Therefore, the development of materials that can achieve both oil-water separation and removal of heavy metal contamination is crucial for industrial applications and environmental sustainability.
Article
Physics, Multidisciplinary
Shanyong Xu et al.
Summary: This study proposes an insulator defect detection algorithm based on an improved MobilenetV1-YOLOv4, which enhances the accuracy and detection speed by introducing lightweight modules and attention mechanisms into the feature extraction process.
Article
Chemistry, Physical
Sergey A. Stel'makh et al.
Summary: This study developed and trained a neural network and an ensemble model to predict the mechanical properties of lightweight fiber-reinforced concrete, achieving high accuracy. It is of great significance for predicting such heterogeneous materials.
Article
Multidisciplinary Sciences
Abdulilah Mohammad Mayet et al.
Summary: This research proposes a detection system for monitoring oil pipelines, which utilizes feature extraction and neural network technology to accurately estimate the types and volume fractions of oil products passing through the pipelines. The system shows significant advantages in terms of accuracy, data interpretation, and cost, increasing its application value in the oil industry.
Article
Chemistry, Multidisciplinary
Jialin Dong et al.
Summary: This article introduces an automated algorithm for real-time monitoring of oil sheen on the water surface and tests its accuracy. By creating an oil sheen image dataset and developing a neural network model, the existence of oil sheen on the water surface was successfully predicted with high accuracy. Additionally, a video-based oil sheen prediction algorithm was developed to autonomously map the spatial distribution of oil sheen.
APPLIED SCIENCES-BASEL
(2022)
Article
Chemistry, Multidisciplinary
Alexey N. Beskopylny et al.
Summary: Machine learning methods have been applied in the construction industry to predict the mechanical properties of building materials, particularly in improving concrete production using artificial intelligence algorithms. This study developed and compared three machine learning algorithms for predicting the compressive strength of concrete, with the k-nearest neighbors algorithm showing the smallest errors and highest coefficient of determination. The developed models can be successfully implemented in the production process and quality control of building materials.
APPLIED SCIENCES-BASEL
(2022)
Article
Engineering, Chemical
Abdulilah Mohammad Mayet et al.
Summary: This study proposes a non-invasive system based on gamma-ray attenuation to detect volumetric percentages in three-phase flows of oil, water, and gas. With the use of neural networks, accurate predictions of volumetric percentages can be made, offering significant implications for the petroleum and petrochemical industries.
Article
Engineering, Mechanical
Dian Jiao et al.
Summary: Online monitoring of multiple lubricant properties is crucial for maintaining and prolonging the health of high-speed rotating and reciprocating machinery in key industries such as aerospace, manufacturing, and energy. A new capacitive oil property sensor array based on a general regression neural network (GRNN) has been developed to accurately and quickly identify acid, base, and water content in lubricant oil. The results show that the GRNN can accurately pinpoint individual oil properties from overlapped sensor array responses.
TRIBOLOGY INTERNATIONAL
(2021)
Article
Environmental Sciences
Zbigniew Otremba et al.
Summary: This study investigated the possibility of detecting oil-in-water emulsions under the sea by modeling the directional distribution of the radiance field above the water surface. By analyzing the optical sea model and the oil emulsion model, the most favorable combination of two wavelengths was identified for determining an index related to polluted sea areas. The study also showed changes in the difference index depending on viewing direction and highlighted the most effective observation directions for detecting emulsions.
Article
Energy & Fuels
Meiyi Qing et al.
JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING
(2020)
Article
Chemistry, Physical
Alexey Beskopylny et al.
Article
Materials Science, Multidisciplinary
Jun Zhu et al.
RESULTS IN PHYSICS
(2020)
Article
Energy & Fuels
Strahinja Markovic et al.
Article
Computer Science, Information Systems
Alexander Buslaev et al.
Article
Chemistry, Analytical
Qing Liu et al.
Article
Energy & Fuels
Qitao Zhang et al.
Article
Engineering, Chemical
Joern Emmerich et al.
CHINESE JOURNAL OF CHEMICAL ENGINEERING
(2019)
Article
Chemistry, Analytical
Prafull Sharma et al.
SENSORS AND ACTUATORS B-CHEMICAL
(2018)
Article
Energy & Fuels
Muhammad Amin Durrani et al.
Proceedings Paper
Business
Yanhui Chen et al.
5TH INTERNATIONAL CONFERENCE ON INFORMATION TECHNOLOGY AND QUANTITATIVE MANAGEMENT, ITQM 2017
(2017)
Article
Energy & Fuels
Gustavo R. Borges et al.
Article
Computer Science, Artificial Intelligence
Furao Shen et al.
Article
Automation & Control Systems
Yu. V. Makeev et al.
AUTOMATION AND REMOTE CONTROL
(2013)
Article
Computer Science, Interdisciplinary Applications
Sebastian Maass et al.
COMPUTERS & CHEMICAL ENGINEERING
(2012)
Article
Biochemical Research Methods
SA Margolis et al.
ANALYTICAL AND BIOANALYTICAL CHEMISTRY
(2003)